mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-20 12:54:11 +08:00
Introduce SVE128 SIMD batch box-cox computation. We've seen about 65% throughput improvement. Privacy Context Container: L1196524 This is a no-op from OSS point of view, therefore it could be landed without tests (see precedence set by https://github.com/pytorch/pytorch/pull/143627), but we should delete those at some point Pull Request resolved: https://github.com/pytorch/pytorch/pull/159778 Approved by: https://github.com/malfet